2014 IEEE Conference on Computer Vision and Pattern Recognition最新文献_第9页

Talking Heads: Detecting Humans and Recognizing Their Interactions 会说话的头:探测人类并识别他们的互动

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.117

Minh Hoai, Andrew Zisserman

引用次数: 60

Image Reconstruction from Bag-of-Visual-Words 视觉词袋图像重建

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.127

Hiroharu Kato, T. Harada

{"title":"Image Reconstruction from Bag-of-Visual-Words","authors":"Hiroharu Kato, T. Harada","doi":"10.1109/CVPR.2014.127","DOIUrl":"https://doi.org/10.1109/CVPR.2014.127","url":null,"abstract":"The objective of this study is to reconstruct images from Bag-of-Visual-Words (BoVW), which is the de facto standard feature for image retrieval and recognition. BoVW is defined here as a histogram of quantized descriptors extracted densely on a regular grid at a single scale. Despite its wide use, no report describes reconstruction of the original image of a BoVW. This task is challenging for two reasons: 1) BoVW includes quantization errors when local descriptors are assigned to visual words. 2) BoVW lacks spatial information of local descriptors when we count the occurrence of visual words. To tackle this difficult task, we use a large-scale image database to estimate the spatial arrangement of local descriptors. Then this task creates a jigsaw puzzle problem with adjacency and global location costs of visual words. Solving this optimization problem is also challenging because it is known as an NP-Hard problem. We propose a heuristic but efficient method to optimize it. To underscore the effectiveness of our method, we apply it to BoVWs extracted from about 100 different categories and demonstrate that it can reconstruct the original images, although the image features lack spatial information and include quantization errors.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"SE-8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126575141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 78

Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition 基于层次参数网络的骨骼关节动作分割与识别

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.98

Di Wu, Ling Shao

引用次数: 206

Diffuse Mirrors: 3D Reconstruction from Diffuse Indirect Illumination Using Inexpensive Time-of-Flight Sensors 漫反射镜:利用廉价的飞行时间传感器从漫射间接照明进行3D重建

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.418

Felix Heide, Lei Xiao, W. Heidrich, M. Hullin

{"title":"Diffuse Mirrors: 3D Reconstruction from Diffuse Indirect Illumination Using Inexpensive Time-of-Flight Sensors","authors":"Felix Heide, Lei Xiao, W. Heidrich, M. Hullin","doi":"10.1109/CVPR.2014.418","DOIUrl":"https://doi.org/10.1109/CVPR.2014.418","url":null,"abstract":"The functional difference between a diffuse wall and a mirror is well understood: one scatters back into all directions, and the other one preserves the directionality of reflected light. The temporal structure of the light, however, is left intact by both: assuming simple surface reflection, photons that arrive first are reflected first. In this paper, we exploit this insight to recover objects outside the line of sight from second-order diffuse reflections, effectively turning walls into mirrors. We formulate the reconstruction task as a linear inverse problem on the transient response of a scene, which we acquire using an affordable setup consisting of a modulated light source and a time-of-flight image sensor. By exploiting sparsity in the reconstruction domain, we achieve resolutions in the order of a few centimeters for object shape (depth and laterally) and albedo. Our method is robust to ambient light and works for large room-sized scenes. It is drastically faster and less expensive than previous approaches using femtosecond lasers and streak cameras, and does not require any moving parts.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"283 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121048632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 177

Gesture Recognition Portfolios for Personalization 个性化的手势识别组合

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.247

Angela Yao, L. Gool, Pushmeet Kohli

引用次数: 33

Capturing Long-Tail Distributions of Object Subcategories 捕获对象子类别的长尾分布

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.122

Xiangxin Zhu, Dragomir Anguelov, Deva Ramanan

引用次数: 162

Segmentation-Free Dynamic Scene Deblurring 无分割动态场景去模糊

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.348

Tae Hyun Kim, Kyoung Mu Lee

{"title":"Segmentation-Free Dynamic Scene Deblurring","authors":"Tae Hyun Kim, Kyoung Mu Lee","doi":"10.1109/CVPR.2014.348","DOIUrl":"https://doi.org/10.1109/CVPR.2014.348","url":null,"abstract":"Most state-of-the-art dynamic scene deblurring methods based on accurate motion segmentation assume that motion blur is small or that the specific type of motion causing the blur is known. In this paper, we study a motion segmentation-free dynamic scene deblurring method, which is unlike other conventional methods. When the motion can be approximated to linear motion that is locally (pixel-wise) varying, we can handle various types of blur caused by camera shake, including out-of-plane motion, depth variation, radial distortion, and so on. Thus, we propose a new energy model simultaneously estimating motion flow and the latent image based on robust total variation (TV)-L1 model. This approach is necessary to handle abrupt changes in motion without segmentation. Furthermore, we address the problem of the traditional coarse-to-fine deblurring framework, which gives rise to artifacts when restoring small structures with distinct motion. We thus propose a novel kernel re-initialization method which reduces the error of motion flow propagated from a coarser level. Moreover, a highly effective convex optimization-based solution mitigating the computational difficulties of the TV-L1 model is established. Comparative experimental results on challenging real blurry images demonstrate the efficiency of the proposed method.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"719 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122996642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 166

Beta Process Multiple Kernel Learning Beta过程多核学习

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.128

Bingbing Ni, Teng Li, P. Moulin

{"title":"Beta Process Multiple Kernel Learning","authors":"Bingbing Ni, Teng Li, P. Moulin","doi":"10.1109/CVPR.2014.128","DOIUrl":"https://doi.org/10.1109/CVPR.2014.128","url":null,"abstract":"In kernel based learning, the kernel trick transforms the original representation of a feature instance into a vector of similarities with the training feature instances, known as kernel representation. However, feature instances are sometimes ambiguous and the kernel representation calculated based on them do not possess any discriminative information, which can eventually harm the trained classifier. To address this issue, we propose to automatically select good feature instances when calculating the kernel representation in multiple kernel learning. Specifically, for the kernel representation calculated for each input feature instance, we multiply it element-wise with a latent binary vector named as instance selection variables, which targets at selecting good instances and attenuate the effect of ambiguous ones in the resulting new kernel representation. Beta process is employed for generating the prior distribution for the latent instance selection variables. We then propose a Bayesian graphical model which integrates both MKL learning and inference for the distribution of the latent instance selection variables. Variational inference is derived for model learning under a max-margin principle. Our method is called Beta process multiple kernel learning. Extensive experiments demonstrate the effectiveness of our method on instance selection and its high discriminative capability for various classification problems in vision.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122997911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Co-segmentation of Textured 3D Shapes with Sparse Annotations 基于稀疏注释的纹理三维形状的协同分割

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.38

M. E. Yümer, Won Chun, A. Makadia

引用次数: 10

Class Specific 3D Object Shape Priors Using Surface Normals 类特定的3D对象形状先验使用表面法线

2014 IEEE Conference on Computer Vision and Pattern Recognition Pub Date : 2014-06-23 DOI: 10.1109/CVPR.2014.89

Christian Häne, Nikolay Savinov, M. Pollefeys

引用次数: 51